[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EDFCTVR2MYM16DR3W30Y6H":3,"skill-same:01M7EDFCTVR2MYM16DR3W30Y6H":49},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":13,"repositoryHtmlUrl":25,"repositoryHomepageUrl":6,"ownerHtmlUrl":26,"ownerBlogUrl":6,"ownerDescription":27,"updatedAt":28,"install":29,"resources":42},"01M7EDFCTVR2MYM16DR3W30Y6H","seo-firecrawl",null,"jonahthan433\u002FCortexOS","jonahthan433","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F211465495?v=4","01M7ECH9HPHGA89DCXHHJBTS3C","jonah.ai","01M7ECH9JCEM45DZMWPT7148S1",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fproductivity\u002Fseo-firecrawl\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"# seo-firecrawl\n\n# Firecrawl Extension for Claude SEO\n\nThis skill requires the Firecrawl extension to be installed:\n```bash\n.\u002Fextensions\u002Ffirecrawl\u002Finstall.sh\n```\n\n**Check availability:** Before using any Firecrawl tool, verify the MCP server\nis connected by checking if `firecrawl_scrape` or any Firecrawl tool\nis available. If tools are not available, inform the user the extension is not\ninstalled and provide install instructions.\n\n## Quick Reference\n\n| Command | Purpose |\n|---------|---------|\n| `\u002Fseo firecrawl crawl \u003Curl>` | Full-site crawl with content extraction |\n| `\u002Fseo firecrawl map \u003Curl>` | Discover site structure (URLs only, fast) |\n| `\u002Fseo firecrawl scrape \u003Curl>` | Single-page scrape with JS rendering |\n| `\u002Fseo firecrawl search \u003Cquery> \u003Curl>` | Search within a crawled site |\n\n## Commands\n\n### crawl -- Full-Site Crawl\n\nCrawl an entire website starting from the given URL. Returns page content,\nmetadata, and links for all discovered pages.\n\n**MCP Tool:** `firecrawl_crawl`\n\n**Parameters:**\n- `url` (required): Starting URL to crawl\n- `limit`: Max pages to crawl (default: 100, max: 500)\n- `maxDepth`: Max link depth from start URL (default: 3)\n- `includePaths`: Array of glob patterns to include (e.g., `[\"\u002Fblog\u002F*\"]`)\n- `excludePaths`: Array of glob patterns to exclude (e.g., `[\"\u002Fadmin\u002F*\", \"\u002Fapi\u002F*\"]`)\n- `scrapeOptions.formats`: Output formats -- `[\"markdown\", \"html\", \"links\"]`\n\n**SEO Usage Patterns:**\n1. **Comprehensive audit crawl**: Crawl full site, extract all pages for subagent analysis\n2. **Section-focused crawl**: Use `includePaths` to audit only `\u002Fblog\u002F*` or `\u002Fproducts\u002F*`\n3. **Broken link detection**: Crawl with `[\"links\"]` format, check all hrefs for 404s\n4. **Content inventory**: Extract all page titles, meta descriptions, H1s at scale\n5. **SPA\u002FJS-rendered sites**: Firecrawl renders JavaScript, solving the Issue #11 problem\n\n**Example orchestration for `\u002Fseo audit`:**\n```\n1. firecrawl_map(url) -> get all URLs (fast, no content)\n2. Filter to top 50 most important pages (homepage, key sections)\n3. firecrawl_crawl(url, limit=50) -> get full content\n4. Feed content to seo-technical, seo-content, seo-schema agents\n```\n\n**Cost awareness:**\n- Free tier: 500 credits\u002Fmonth\n- 1 credit = 1 page crawled or scraped\n- Map operations are cheaper (0.5 credits per URL discovered)\n- Always inform user of estimated credit usage before large crawls\n\n### map -- Site Structure Discovery\n\nDiscover all URLs on a website without fetching content. Fast and credit-efficient.\n\n**MCP Tool:** `firecrawl_map`\n\n**Parameters:**\n- `url` (required): Website URL to map\n- `limit`: Max URLs to discover (default: 5000)\n- `search`: Optional search term to filter URLs\n\n**SEO Usage Patterns:**\n1. **Sitemap comparison**: Map site, compare discovered URLs vs XML sitemap\n2. **Orphan page detection**: URLs in sitemap but not linked from any page\n3. **Crawl budget analysis**: Total indexable pages vs pages linked from homepage\n4. **URL pattern analysis**: Identify URL structure patterns, duplicates, parameter bloat\n5. **Pre-audit discovery**: Run map first, then targeted crawl on key sections\n\n**Output:** Array of URLs. Present as:\n```\nSite: example.com\nPages discovered: 342\n\nURL Pattern Breakdown:\n  \u002Fblog\u002F*          - 128 pages (37%)\n  \u002Fproducts\u002F*      - 89 pages (26%)\n  \u002Fcategory\u002F*      - 45 pages (13%)\n  \u002Fpages\u002F*         - 32 pages (9%)\n  \u002F (root pages)   - 48 pages (14%)\n```\n\n### scrape -- Single-Page Deep Scrape\n\nScrape a single page with full JavaScript rendering. More thorough than\n`fetch_page.py` because it executes JS and waits for dynamic content.\n\n**MCP Tool:** `firecrawl_scrape`\n\n**Parameters:**\n- `url` (required): Page URL to scrape\n- `formats`: Output formats -- `[\"markdown\", \"html\", \"links\", \"screenshot\"]`\n- `onlyMainContent`: Strip nav\u002Ffooter\u002Fsidebar (default: true)\n- `waitFor`: CSS selector or milliseconds to wait for content\n- `timeout`: Request timeout in ms (default: 30000)\n- `actions`: Browser actions before scraping (click, scroll, wait)\n\n**SEO Usage Patterns:**\n1. **SPA content extraction**: Scrape JS-rendered React\u002FVue\u002FAngular pages\n2. **Dynamic content audit**: Pages with lazy-loaded content below the fold\n3. **Paywall\u002Flogin detection**: Identify content behind authentication walls\n4. **Main content extraction**: Use `onlyMainContent` for clean E-E-A-T analysis\n5. **Screenshot capture**: Use `screenshot` format for visual analysis\n\n**When to use scrape vs fetch_page.py:**\n| Scenario | Use |\n|----------|-----|\n| Static HTML page | `fetch_page.py` (no API cost) |\n| JS-rendered SPA | `firecrawl_scrape` (renders JS) |\n| Need response headers | `fetch_page.py` (returns headers) |\n| Need clean markdown | `firecrawl_scrape` (better extraction) |\n| Rate-limited\u002Fblocked | `firecrawl_scrape` (handles anti-bot) |\n\n### search -- Site-Scoped Search\n\nSearch within a website for specific content. Useful for finding pages\nrelated to a topic without crawling everything.\n\n**MCP Tool:** `firecrawl_search`\n\n**Parameters:**\n- `query` (required): Search query\n- `url` (required): Website to search within\n- `limit`: Max results (default: 10)\n- `scrapeOptions.formats`: Output format for matched pages\n\n**SEO Usage Patterns:**\n1. **Content gap validation**: Search for a keyword on the site to check if content exists\n2. **Internal linking opportunities**: Find pages mentioning a topic that could link to each other\n3. **Duplicate content detection**: Search for key phrases to find near-duplicates\n4. **Competitor content research**: Search competitor site for specific topics\n\n## Cross-Skill Integration\n\n### With seo-audit (full audit)\nWhen Firecrawl is available during `\u002Fseo audit`:\n1. Use `firecrawl_map` to discover all site URLs\n2. Compare with XML sitemap (seo-sitemap) to find orphan\u002Fmissing pages\n3. Select top pages for deep analysis\n4. Feed crawled content to all subagents (technical, content, schema, geo)\n5. Report total crawlable pages, URL patterns, and crawl depth\n\n### With seo-technical\n- Broken link detection: crawl all internal links, check for 404s\n- Redirect chain mapping: follow all redirects, flag chains > 2 hops\n- Mixed content detection: check HTTP resources on HTTPS pages\n- Canonical verification: compare canonical URLs with actual URLs\n\n### With seo-sitemap\n- Sitemap coverage: % of crawled pages present in sitemap\n- Orphan pages: pages found by crawl but missing from sitemap\n- Stale sitemap entries: URLs in sitemap that return 404\u002F410\n\n### With seo-content\n- Content extraction: feed clean markdown to E-E-A-T analysis\n- Thin content detection: identify pages with \u003C 300 words at scale\n- Duplicate content: compare content across pages for near-duplicates\n\n### With seo-schema\n- Schema extraction: pull JSON-LD from all crawled pages\n- Schema coverage: % of pages with structured data\n- Schema validation: batch-validate extracted schemas\n\n## Error Handling\n\n| Error | Cause | Resolution |\n|-------|-------|-----------|\n| `FIRECRAWL_API_KEY not set` | MCP not configured | Run `.\u002Fextensions\u002Ffirecrawl\u002Finstall.sh` |\n| `402 Payment Required` | Credits exhausted | Check usage at firecrawl.dev\u002Fapp, upgrade plan |\n| `429 Too Many Requests` | Rate limited | Wait 60s, reduce crawl concurrency |\n| `408 Timeout` | Page too slow to render | Increase `timeout`, try without JS rendering |\n| `403 Forbidden` | Site blocks crawling | Check robots.txt, may need to skip this site |\n\n**Graceful fallback:** If Firecrawl is unavailable, inform the user and suggest:\n1. Use `fetch_page.py` for single-page analysis (no API cost)\n2. Use `WebFetch` tool for basic HTML retrieval\n3. Install Firecrawl: `.\u002Fextensions\u002Ffirecrawl\u002Finstall.sh`\n",{},"main","38b32c99e7ed0b8e215d638e92cfa452c1ec3079","skills\u002Fimported\u002Fproductivity\u002Fseo-firecrawl","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS","https:\u002F\u002Fgithub.com\u002Fjonahthan433","AI Consultant","2026-10-24 05:13:39",{"source":7,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add jonahthan433\u002FCortexOS --skill seo-firecrawl",{"tool":35,"command":36},"bunx","bunx skills add jonahthan433\u002FCortexOS --skill seo-firecrawl",{"tool":38,"command":39},"pnpm","pnpm dlx skills add jonahthan433\u002FCortexOS --skill seo-firecrawl","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fproductivity\u002Fseo-firecrawl\u002FSKILL.md",true,[43],{"path":44,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":47,"sourceHtmlUrl":48},"skill.json","REFERENCE","参考文档",288,"https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fproductivity\u002Fseo-firecrawl\u002Fskill.json",[50,56,62,68,74,80],{"skillNo":51,"name":52,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":18},"01M7EDQZDQX3Q8Y7GCQX6KN9V7","opportunity-brief","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fsales\u002Fopportunity-brief\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":18},"01M7EDQYA0V9Y99VKBREJJ3MRT","morning-intel","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Fmorning-intel\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M7EDQVX1JVY0B6PDHKKGM19G","decision-brief","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Fdecision-brief\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M7EDQV1GENZAC2SZSD8KZ3GM","weekly-review","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fweekly-review\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M7EDQT2KETJ1Y3CGVN9EKW2J","system-health","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fops\u002Fsystem-health\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7EDQQN2JK3XPWMS1M4T0F3K","backup-restore","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fops\u002Fbackup-restore\u002FSKILL.md",[],[]]